state: generation 5944 (cycle)

2026-09-12 00:45:20 +00:00
parent 296914ca14
commit a8709adb37
9 changed files with 2120 additions and 2056 deletions
--- a/.modelhub_state/outcome_checkpoint.json
+++ b/.modelhub_state/outcome_checkpoint.json
@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-09-11T23:52:34.245335+00:00",
-  "lastSyncTime": "2026-09-11T23:52:34.207615+00:00",
+  "generatedAt": "2026-09-12T00:43:33.454278+00:00",
+  "lastSyncTime": "2026-09-12T00:43:33.238151+00:00",
  "recentLimit": 300,
  "report": {
    "architectureCompatibilityBlocks": {
@@ -1813,6 +1813,27 @@
        "total": 167,
        "unresolvedFailureCount": 68
      },
+      "Iluvatar_mrv-100|vllm|text-generation": {
+        "attributableFailureCount": 1,
+        "decisionFailureRate": 1.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 1,
+        "failureBreakdown": {
+          "model_load": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Iluvatar_mrv-100",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
      "Kunlunxin_p-800|unknown|text-generation": {
        "attributableFailureCount": 1,
        "decisionFailureRate": 1.0,
@@ -2316,30 +2337,30 @@
        "unresolvedFailureCount": 862
      },
      "vllm": {
-        "attributableFailureCount": 243,
-        "decisionFailureRate": 0.9878,
-        "decisionSuccessRate": 0.0122,
-        "decisionTotal": 246,
+        "attributableFailureCount": 244,
+        "decisionFailureRate": 0.9879,
+        "decisionSuccessRate": 0.0121,
+        "decisionTotal": 247,
        "failureBreakdown": {
          "ambiguous_runtime": 195,
          "backend_operator": 33,
          "framework_architecture_unsupported": 171,
          "memory_capacity": 6,
-          "model_load": 18,
+          "model_load": 19,
          "platform_infrastructure": 1,
          "repository_structure": 5,
          "runtime_memory": 6,
          "tokenizer_compatibility": 4,
          "参数/模板问题": 24
        },
-        "failureCount": 463,
+        "failureCount": 464,
        "failureRate": 0.9936,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 1,
        "successCount": 3,
        "successRate": 0.0064,
-        "total": 466,
+        "total": 467,
        "unresolvedFailureCount": 219
      },
      "vllm-mlu": {
@@ -2443,7 +2464,7 @@
        "unresolvedFailureCount": 1
      }
    },
-    "generatedAt": "2026-09-11T23:52:34.241290+00:00",
+    "generatedAt": "2026-09-12T00:43:33.449427+00:00",
    "gpuSummaries": {
      "Ascend_910-b3": {
        "attributableFailureCount": 26,
@@ -2606,27 +2627,27 @@
        "unresolvedFailureCount": 44
      },
      "Iluvatar_mrv-100": {
-        "attributableFailureCount": 87,
-        "decisionFailureRate": 0.8878,
-        "decisionSuccessRate": 0.1122,
-        "decisionTotal": 98,
+        "attributableFailureCount": 88,
+        "decisionFailureRate": 0.8889,
+        "decisionSuccessRate": 0.1111,
+        "decisionTotal": 99,
        "failureBreakdown": {
          "ambiguous_runtime": 19,
          "framework_architecture_unsupported": 49,
          "memory_capacity": 1,
-          "model_load": 37,
+          "model_load": 38,
          "platform_infrastructure": 1,
          "参数/模板问题": 2,
          "验证失败": 47
        },
-        "failureCount": 156,
-        "failureRate": 0.9341,
+        "failureCount": 157,
+        "failureRate": 0.9345,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 1,
        "successCount": 11,
-        "successRate": 0.0659,
-        "total": 167,
+        "successRate": 0.0655,
+        "total": 168,
        "unresolvedFailureCount": 68
      },
      "Kunlunxin_p-800": {
@@ -3246,6 +3267,29 @@
        "total": 1,
        "unresolvedFailureCount": 1
      },
+      "Iluvatar_mrv-100|vllm|text-generation|hrm_text|none": {
+        "attributableFailureCount": 1,
+        "decisionFailureRate": 1.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 1,
+        "failureBreakdown": {
+          "model_load": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm",
+        "modelType": "hrm_text",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Iluvatar_mrv-100",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
      "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|aquila3|none": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
@@ -5692,6 +5736,30 @@
        "total": 1,
        "unresolvedFailureCount": 1
      },
+      "Iluvatar_mrv-100|vllm|text-generation|hrm_text|none|31": {
+        "attributableFailureCount": 1,
+        "decisionFailureRate": 1.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 1,
+        "failureBreakdown": {
+          "model_load": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm",
+        "loadSizeLog2Bucket": 31,
+        "modelType": "hrm_text",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Iluvatar_mrv-100",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
      "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|aquila3|none|12": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
@@ -6987,19 +7055,19 @@
        "unresolvedFailureCount": 0
      }
    },
-    "terminalRecords": 1668,
-    "totalRecords": 1755,
+    "terminalRecords": 1669,
+    "totalRecords": 1756,
    "totals": {
-      "attributableFailureCount": 441,
-      "decisionFailureRate": 0.8891,
-      "decisionSuccessRate": 0.1109,
-      "decisionTotal": 496,
+      "attributableFailureCount": 442,
+      "decisionFailureRate": 0.8893,
+      "decisionSuccessRate": 0.1107,
+      "decisionTotal": 497,
      "failureBreakdown": {
        "ambiguous_runtime": 394,
        "backend_operator": 40,
        "framework_architecture_unsupported": 276,
        "memory_capacity": 11,
-        "model_load": 61,
+        "model_load": 62,
        "platform_infrastructure": 4,
        "repository_structure": 5,
        "runtime_memory": 6,
@@ -7007,31 +7075,30 @@
        "参数/模板问题": 101,
        "验证失败": 673
      },
-      "failureCount": 1613,
+      "failureCount": 1614,
      "failureRate": 0.967,
      "pendingCount": 0,
      "pendingRate": 0.0,
      "platformFailureCount": 4,
      "successCount": 55,
      "successRate": 0.033,
-      "total": 1668,
+      "total": 1669,
      "unresolvedFailureCount": 1168
    },
    "warnings": [
      "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
      "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
      "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
+      "GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
      "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
      "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
      "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
-      "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
      "GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
-      "GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
-      "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
      "GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
-      "GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
+      "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
+      "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
+      "GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
      "组合 Iluvatar_mrv-100|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
-      "组合 Cambricon_mlu-370-x4|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
      "组合 Mthreads_s4000|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
      "组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
      "组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -7046,10 +7113,11 @@
      "组合 hygon_k100-ai|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
      "组合 Iluvatar_bi-150|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
      "组合 Vastai_va16|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
+      "组合 Cambricon_mlu-370-x4|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
      "组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
    ]
  },
  "storageMode": "decision_state_only",
-  "summarizedRecords": 1755,
+  "summarizedRecords": 1756,
  "version": 1
 }